CN113111928A - Semi-supervised learning mineral resource quantitative prediction method based on geoscience database - Google Patents
Semi-supervised learning mineral resource quantitative prediction method based on geoscience database Download PDFInfo
- Publication number
- CN113111928A CN113111928A CN202110353244.8A CN202110353244A CN113111928A CN 113111928 A CN113111928 A CN 113111928A CN 202110353244 A CN202110353244 A CN 202110353244A CN 113111928 A CN113111928 A CN 113111928A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- probability
- steps
- database
- prediction method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 229910052500 inorganic mineral Inorganic materials 0.000 title claims abstract description 35
- 239000011707 mineral Substances 0.000 title claims abstract description 35
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 36
- 238000005457 optimization Methods 0.000 claims abstract description 11
- 230000009286 beneficial effect Effects 0.000 claims abstract description 8
- 230000000694 effects Effects 0.000 claims abstract description 6
- 230000001186 cumulative effect Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 8
- 238000007637 random forest analysis Methods 0.000 claims description 5
- 238000011160 research Methods 0.000 claims description 5
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 230000002349 favourable effect Effects 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims 1
- 230000007547 defect Effects 0.000 description 2
- 238000011234 economic evaluation Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000033558 biomineral tissue development Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Remote Sensing (AREA)
- Geophysics And Detection Of Objects (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a semi-supervised learning mineral resource quantitative prediction method based on a geoscience database, which comprises the following steps: the method consists of three parts, wherein the first part is a basic algorithm; the second part is a Bayesian hyper-parameter optimization algorithm; the third part is a probability-area/volume graph method for evaluating the effect of the prediction method and delineating the beneficial target area of the ore exploration, and the method has the following beneficial effects: the accuracy and the efficiency of mineral resource exploration can be finally improved by the semi-supervised learning mineral resource quantitative prediction method based on the geoscience database, which is formed by the three methods, and the three methods through the input of computer software.
Description
Technical Field
The invention relates to the field of mineral resource exploration, in particular to a semi-supervised learning mineral resource quantitative prediction method based on a geological database.
Background
Mineral resource exploration is to find mineral deposits and find out mineral body distribution, mineral types, quality, quantity, mining and utilizing conditions, technical and economic evaluation, application prospect and the like in the mineral deposits, and all geological exploration work required by national construction or mine enterprises is met. Mineral resources are buried underground, and have the characteristics of sparseness, concealment, complexity and the like, methods such as geological mapping, geophysical prospecting, chemical prospecting, remote sensing geology and the like are often required in the exploration process, technical means such as drilling, pit prospecting and the like are applied, the work such as measurement, cataloging, sampling, chemical examination, experiments, reserve calculation, technical and economic evaluation, feasibility research and the like is required, and a large amount of manpower, material resources and capital investment is required. And a mineral resource needs to pass through a long period from discovery, finding out to development. Thus, mineral resource exploration is a risky task. Therefore, it is important to implement the principle of circular economy in the mineral resource exploration stage.
At present, mineral resource exploration is inaccurate, and mineral resource exploration efficiency is low, so a brand-new mineral resource exploration method needs to be designed for the defects.
Disclosure of Invention
Aiming at the defects of the existing application and technology, the invention provides a semi-supervised learning mineral resource quantitative prediction method based on a geoscience database. The method can well solve the problems of inaccurate mineral resource exploration and low mineral resource exploration efficiency. Based on the scheme, the user can input the program through the computer software, so that the user can safely carry out synchronous operation by means of a mobile phone or a computer terminal, and the method has very important significance for improving the accuracy and efficiency of mineral resource exploration.
In order to achieve the purpose, the invention provides the following technical scheme:
a semi-supervised learning mineral resource quantitative prediction method based on a geo-database comprises the following steps: the method consists of three parts, wherein the first part is a basic algorithm; the second part is a Bayesian hyper-parameter optimization algorithm; the third section is a probability-area/volume mapping method for evaluating the effectiveness of the prediction method and delineating the target area favorable to the given mine.
The method comprises the following steps: basic algorithm: a positive sample label-free learning algorithm based on a 'bagging method';
wherein, the 'bagging method' comprises the following calculation flow of the algorithm:
the second method comprises the following steps: the Bayesian hyper-parameter optimization algorithm is summarized in the following brief steps:
the method comprises the following steps: random some hyper-parameters x and training to obtain models, and then describing the capability y of the models to obtain a priori data set D ═ x1, y1), (x2, y2),. ·, (xk, yk);
step two: fitting a Gaussian model GM through prior data D;
step three: finding a maximum value under the GM, a hyper-parameter x ' through an acquisition function, obtaining a model and a depicting model capability y ' through x ' training, and adding (x ', y ') into a data set D;
step four: repeating the steps 2-3 until the condition is terminated.
Further, a third method, namely a probability-area/volume map method for evaluating the effect of the prediction method and defining the beneficial target area of the ore exploration, is briefly summarized as follows: the probability volume graph comprises two lines, wherein one line is the percentage of the block area/volume corresponding to the predicted cumulative probability in an ore body, the other line is the percentage of the block area/volume corresponding to the predicted cumulative probability in a research area, the intersection point of the two lines is the probability threshold corresponding to the target area, and the higher the intersection point is, the better the algorithm performance is.
Further, for basic algorithms, the method provides algorithms such as random forests, gradient lifting trees, support vector machines and the like commonly used in quantitative prediction of two-dimensional and three-dimensional mineral resources.
The invention has the beneficial effects that:
the invention combines a basic algorithm, a Bayesian super-parameter optimization algorithm and a probability-area/volume graph method for evaluating the effect of a prediction method and delineating a beneficial target area of a given ore into a total method, wherein the basic algorithm is a positive sample label-free learning algorithm based on a 'bagging method', and the Bayesian super-parameter optimization algorithm comprises four steps: the method comprises the following steps: random some hyper-parameters x and training to obtain models, and then describing the capability y of the models to obtain a priori data set D ═ x1, y1), (x2, y2),. ·, (xk, yk); step two: fitting a Gaussian model GM through prior data D; step three: finding a maximum value under the GM, a hyper-parameter x ' through an acquisition function, obtaining a model and a depicting model capability y ' through x ' training, and adding (x ', y ') into a data set D; step four: repeating the steps 2-3 until the termination condition, and using the probability-area/volume graph method for evaluating the prediction method effect and defining the beneficial target area of the ore-finding ore, wherein the method is briefly summarized as follows: the probability volume graph comprises two lines, wherein one line is the percentage of the block area/volume corresponding to the predicted cumulative probability to the ore body, the other line is the percentage of the block area/volume corresponding to the predicted cumulative probability to the research area, the intersection point of the two lines is the probability threshold corresponding to the target area, the higher the intersection point is, the better the algorithm performance is, the more the semi-supervised learning mineral resource quantitative prediction method based on the geoscience database, which is formed by the three methods, and the accuracy and the efficiency of mineral resource exploration can be finally improved by inputting the three methods through computer software.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a synchronous English flow chart of the Bayesian hyper-parameter optimization algorithm of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, the semi-supervised learning mineral resource quantitative prediction method based on the geo-database includes: the method consists of three parts, wherein the first part is a basic algorithm; the second part is a Bayesian hyper-parameter optimization algorithm; the third section is a probability-area/volume mapping method for evaluating the effectiveness of the prediction method and delineating the target area favorable to the given mine.
The method comprises the following steps: basic algorithm: a positive sample label-free learning algorithm based on a 'bagging method';
wherein, the 'bagging method' comprises the following calculation flow of the algorithm:
the second method comprises the following steps: the Bayesian hyper-parameter optimization algorithm is summarized in the following brief steps:
the method comprises the following steps: random some hyper-parameters x and training to obtain models, and then describing the capability y of the models to obtain a priori data set D ═ x1, y1), (x2, y2),. ·, (xk, yk);
step two: fitting a Gaussian model GM through prior data D;
step three: finding a maximum value under the GM, a hyper-parameter x ' through an acquisition function, obtaining a model and a depicting model capability y ' through x ' training, and adding (x ', y ') into a data set D;
step four: repeating the steps 2-3 until the condition is terminated.
Preferably, the third method is a probability-area/volume map method for evaluating the effect of the prediction method and delineating the beneficial target area of the given ore, which is briefly summarized as follows: the probability volume graph comprises two lines, wherein one line is the percentage of the block area/volume corresponding to the predicted cumulative probability in an ore body, the other line is the percentage of the block area/volume corresponding to the predicted cumulative probability in a research area, the intersection point of the two lines is the probability threshold corresponding to the target area, and the higher the intersection point is, the better the algorithm performance is.
Preferably, for the basic algorithm, the method provides algorithms such as random forests, gradient lifting trees, support vector machines and the like commonly used in quantitative prediction of two-dimensional and three-dimensional mineral resources.
The invention uses computer software to run and internally comprise modules such as data preprocessing, Bayesian optimization, positive sample label-free learning based on 'bagging method', probability-area/volume method and the like on an Anaconda3 Spyder4.1.4 platform, wherein the basic learners of the two types of positive sample label-free learning comprise Random Forest (RF), Gradient Boosting Decision Tree (GBDT) and Support Vector Machine (SVM) which are most widely applied in quantitative prediction and evaluation of mineral resources at present, and the three basic learners are constructed, trained and constructed and trained by using a Machine learning library scimit-lean.
First, spyder4.1.4, then the source data (example) software of the software is input, and the following are required to be respectively input: csv format, a. a. a mineralogy information database; b. a database of unlabeled geoscience information; c. x, Y, Z (i.e., depth) coordinate information for all data (in ore body first followed by no tag order). Note here that the feature categories in the ore body geography information database and the unlabeled geography information database should be consistent, the above data and the software are all placed in the same operation directory, the bag-pack method positive sample unlabeled learning module is operated, the P-V plot module is operated, and finally, a data result is obtained, and the final processing result of the software is: the csv format file has X, Y and Z and mineralization probability, and the aims of improving the accuracy and efficiency of mineral resource exploration can be finally achieved through the three methods of inputting computer software.
In the description of the invention, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted", "connected" and "connected" are to be construed broadly, e.g. as being fixed or detachable or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the creation of the present invention can be understood by those of ordinary skill in the art through specific situations.
It should be noted that, in the present specification, the terms "upper", "lower", "inner", "outer", "front end", "rear end", "both ends", "one end", "the other end", etc. indicate the orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and operate, and thus, should not be construed as limiting the present invention.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (3)
1. A semi-supervised learning mineral resource quantitative prediction method based on a geo database is characterized in that the processing method comprises the following steps: the method consists of three parts, wherein the first part is a basic algorithm; the second part is a Bayesian hyper-parameter optimization algorithm; the third section is a probability-area/volume mapping method for evaluating the effectiveness of the prediction method and delineating the target area favorable to the given mine.
The method comprises the following steps: basic algorithm: a positive sample label-free learning algorithm based on a 'bagging method';
wherein, the 'bagging method' comprises the following calculation flow of the algorithm:
the second method comprises the following steps: the Bayesian hyper-parameter optimization algorithm is summarized in the following brief steps:
the method comprises the following steps: random some hyper-parameters x and training to obtain models, and then describing the capability y of the models to obtain a priori data set D ═ x1, y1), (x2, y2),. ·, (xk, yk);
step two: fitting a Gaussian model GM through prior data D;
step three: finding a maximum value under the GM, a hyper-parameter x ' through an acquisition function, obtaining a model and a depicting model capability y ' through x ' training, and adding (x ', y ') into a data set D;
step four: repeating the steps 2-3 until the condition is terminated.
2. The semi-supervised learning mineral resource quantitative prediction method based on the geoscience database as recited in claim 1, wherein: the third method is a probability-area/volume graph method for evaluating the effect of the prediction method and defining the beneficial target area of the ore exploration, and is briefly summarized as follows: the probability volume graph comprises two lines, wherein one line is the percentage of the block area/volume corresponding to the predicted cumulative probability in an ore body, the other line is the percentage of the block area/volume corresponding to the predicted cumulative probability in a research area, the intersection point of the two lines is the probability threshold corresponding to the target area, and the higher the intersection point is, the better the algorithm performance is.
3. The semi-supervised learning mineral resource quantitative prediction method based on the geoscience database as recited in claim 1, wherein: for basic algorithms, the method provides algorithms such as random forests, gradient lifting trees, support vector machines and the like which are commonly used in quantitative prediction of two-dimensional and three-dimensional mineral resources.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110353244.8A CN113111928B (en) | 2021-04-01 | 2021-04-01 | Semi-supervised learning mineral resource quantitative prediction method based on geometrics database |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110353244.8A CN113111928B (en) | 2021-04-01 | 2021-04-01 | Semi-supervised learning mineral resource quantitative prediction method based on geometrics database |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113111928A true CN113111928A (en) | 2021-07-13 |
| CN113111928B CN113111928B (en) | 2023-12-29 |
Family
ID=76713790
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110353244.8A Active CN113111928B (en) | 2021-04-01 | 2021-04-01 | Semi-supervised learning mineral resource quantitative prediction method based on geometrics database |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113111928B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115859106A (en) * | 2022-12-05 | 2023-03-28 | 中国地质大学（北京） | Mineral exploration method and device based on semi-supervised learning and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109936582A (en) * | 2019-04-24 | 2019-06-25 | 第四范式（北京）技术有限公司 | Construct the method and device based on the PU malicious traffic stream detection model learnt |
| CN110084374A (en) * | 2019-04-24 | 2019-08-02 | 第四范式（北京）技术有限公司 | Construct method, apparatus and prediction technique, device based on the PU model learnt |
| KR20190118937A (en) * | 2018-04-11 | 2019-10-21 | 삼성에스디에스 주식회사 | System and method for optimization of hyperparameter |
| CN111105037A (en) * | 2018-10-25 | 2020-05-05 | 罗伯特·博世有限公司 | Method for machine learning by a gaussian process |
| CN111652317A (en) * | 2020-06-04 | 2020-09-11 | 郑州科技学院 | Hyper-parameter image segmentation method based on Bayesian deep learning |
| CN112215365A (en) * | 2020-10-28 | 2021-01-12 | 天津大学 | Method for providing feature prediction capability based on naive Bayes model |
| CN112561082A (en) * | 2020-12-22 | 2021-03-26 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for generating model |
-
2021
- 2021-04-01 CN CN202110353244.8A patent/CN113111928B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20190118937A (en) * | 2018-04-11 | 2019-10-21 | 삼성에스디에스 주식회사 | System and method for optimization of hyperparameter |
| CN111105037A (en) * | 2018-10-25 | 2020-05-05 | 罗伯特·博世有限公司 | Method for machine learning by a gaussian process |
| CN109936582A (en) * | 2019-04-24 | 2019-06-25 | 第四范式（北京）技术有限公司 | Construct the method and device based on the PU malicious traffic stream detection model learnt |
| CN110084374A (en) * | 2019-04-24 | 2019-08-02 | 第四范式（北京）技术有限公司 | Construct method, apparatus and prediction technique, device based on the PU model learnt |
| CN111652317A (en) * | 2020-06-04 | 2020-09-11 | 郑州科技学院 | Hyper-parameter image segmentation method based on Bayesian deep learning |
| CN112215365A (en) * | 2020-10-28 | 2021-01-12 | 天津大学 | Method for providing feature prediction capability based on naive Bayes model |
| CN112561082A (en) * | 2020-12-22 | 2021-03-26 | 北京百度网讯科技有限公司 | Method, device, equipment and storage medium for generating model |
Non-Patent Citations (7)
| Title |
|---|
| J. C. BARSCE等: "Towards autonomous reinforcement learning: Automatic setting of hyper-parameters using Bayesian optimization", 《2017 XLIII LATIN AMERICAN COMPUTER CONFERENCE (CLEI)》 * |
| MORDELET F等: "A bagging SVM to learn from positive and unlabeled examples", 《PATTERN RECOGNITION LETTERS》 * |
| YOUSEFI M等: "Prediction–area (P–A) plot and C–A fractal analysis to classify and evaluate evidential maps for mineral prospectivity modeling", 《COMPUTERS & GEOSCIENCES》 * |
| ZHANG W等: "Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization", 《GEOSCIENCE FRONTIERS》 * |
| ZHANG Z等: "Bagging-based positive-unlabeled learning algorithm with Bayesian hyperparameter optimization for three-dimensional mineral potential mapping", 《COMPUTERS & GEOSCIENCES》 * |
| 赵永翼等: "基于CART和PU算法的矿石矿物的智能识别", 《沈阳师范大学学报：自然科学版》 * |
| 马瑶等: "机器学习方法在矿产资源定量预测应用研究进展", 《地质科技通报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115859106A (en) * | 2022-12-05 | 2023-03-28 | 中国地质大学（北京） | Mineral exploration method and device based on semi-supervised learning and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113111928B (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xiao et al. | GIS-based 3D prospectivity mapping: A case study of Jiama copper-polymetallic deposit in Tibet, China | |
| CN110490100A (en) | Ground automatic identification based on deep learning names method and system | |
| MX2015003997A (en) | Analyzing microseismic data from a fracture treatment. | |
| CN116665067B (en) | Ore finding target area optimization system and method based on graph neural network | |
| CN112652066B (en) | Three-dimensional geological model-based geological characterization condition evaluation method and system | |
| Yang et al. | Quantification of uncertainty associated with evidence layers in mineral prospectivity mapping using direct sampling and convolutional neural network | |
| CN117576335B (en) | Three-dimensional space model data processing method and system for mineral area investigation | |
| CN116245013A (en) | Geological prediction model construction method, modeling method, equipment and storage medium | |
| Chen et al. | Rock image classification using deep residual neural network with transfer learning | |
| CN113902861A (en) | Three-dimensional geological modeling method based on machine learning | |
| Liu et al. | Developments in quantitative assessment and modeling of mineral resource potential: an overview | |
| Zhang et al. | Comparison of 3D prospectivity modeling methods for Fe-Cu skarn deposits: A case study of the Zhuchong Fe-Cu deposit in the Yueshan orefield (Anhui), eastern China | |
| Hajihosseinlou et al. | A novel scheme for mapping of MVT-type Pb–Zn prospectivity: LightGBM, a highly efficient gradient boosting decision tree machine learning algorithm | |
| CN113111928A (en) | Semi-supervised learning mineral resource quantitative prediction method based on geoscience database | |
| CN110490241A (en) | A kind of horizontal well parameter optimization method and device | |
| Pan et al. | Intelligent rock fracture identification based on image semantic segmentation: methodology and application | |
| AlSalmi et al. | Automated seismic semantic segmentation using attention U-Net | |
| WO2022178507A1 (en) | Geologic learning framework | |
| Zhang et al. | Lithology identification technology of logging data based on deep learning model | |
| Xu et al. | The use of 3D convolutional autoencoder in fault and fracture network characterization | |
| CN117574269B (en) | Intelligent identification method and system for natural cracks of land shale reservoir | |
| CN116090662B (en) | Knowledge-graph-based method and system for predicting potential of copper mine outside environment and electronic equipment | |
| Chen et al. | Statistic Ratio Attention Guided Siamese U-Net for SAR Image Semantic Change Detection | |
| ZENG et al. | Machine learning in identifying and mapping the surface rupture of the 2021 M W 7.4 Madoi earthquake, Qinghai | |
| CN115828072B (en) | Reconstruction method of missing section of unconventional logging curve and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |